© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27404
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -1.31
     other
    -1.06
     more
    -1.06
     those
    -1.05
     μαύ
    -0.97
    郿
    -0.95
     fundamentales
    -0.95
     Missed
    -0.94
     auch
    -0.93
    Beskrivning
    -0.93
    POSITIVE LOGITS
    addCriterion
    1.14
    @[+][
    1.10
    лиза
    1.01
    ٥
    0.97
    ⎞
    0.96
     alimentare
    0.96
    utschland
    0.94
    </b>
    0.94
     HEIGHT
    0.93
    क
    0.93
    Activations Density 0.042%

    No Known Activations